Paper: arXiv 2411.13180
Authors: Szymon Lis
Abstract
This study conducted a comprehensive review of 71 papers published between 2000 and 2021 that employed various measures of investor sentiment to model returns. The analysis indicates that higher complexity of sentiment measures and models improves the coefficient of determination. However, there was insufficient evidence to support that models incorporating more complex sentiment measures have better predictive power than those employing simpler proxies. Additionally, the significance of sentiment varies based on the asset and time period being analyzed, suggesting that the consensus relying on the BW index as a sentiment measure may be subject to change.
Complexity vs Empirical Score
- Math Complexity: 3.5/10
- Empirical Rigor: 2.0/10
- Quadrant: Philosophers — conceptual discussion, lower math and empirical scores
Why this score: The paper is a literature review that discusses complex asset pricing models and behavioral theories but does not present new mathematical derivations or implementations, resulting in low math complexity and low empirical rigor.
Research Flowchart
flowchart TD
A["Research Goal: Review 71 papers (2000-2021)<br>Assess Investor Sentiment in Asset Pricing"] --> B["Data: BW Index & Other Proxies<br>Applied to Equities/Assets"]
B --> C["Methodology: Comparative Analysis<br>Simple vs. Complex Sentiment Models"]
C --> D{"Computational Processes<br>Model Estimation & Validation"}
D --> E["Key Finding 1: Complexity ↑ R²<br>(Model Fit Improves)"]
D --> F["Key Finding 2: Complexity ↛<br>Better Predictive Power"]
D --> G["Key Finding 3: Significance varies<br>by Asset & Time Period"]
E --> H["Outcome: BW Index Consensus<br>May Shift; Context-Dependent Validity"]
F --> H
G --> H
Evidence Card
What the authors claim, on what data, and who has checked it. Read from the paper's own text by a language model: every quote is verbatim, nothing was re-run. How to read this card
Proposes
The paper provides a comprehensive review of 71 empirical studies on investor sentiment and asset pricing models published between 2000 and 2021.
Source sentence
This study conducted a comprehensive review of 71 papers published between 2000 and 2021 that employed various measures of investor sentiment to model returns.
Assumes
No explicit assumptions found in the text.
Data
No dataset named in the text.
Costs
Not applicable
Finds 5
- Higher complexity of sentiment measures and models improves the coefficient of determination. statistical
Source sentence
The analysis indicates that higher complexity of sentiment measures and models improves the coefficient of determination.
- There is insufficient evidence that models with more complex sentiment measures have better predictive power than those using simpler proxies. predictive-accuracy
Source sentence
However, there was insufficient evidence to support that models incorporating more complex sentiment measures have better predictive power than those employing simpler proxies.
- The significance of sentiment varies across assets and time periods, challenging the consensus reliance on the BW index. statistical
Source sentence
Additionally, the significance of sentiment varies based on the asset and time period being analyzed, suggesting that the consensus relying on the BW index as a sentiment measure may be subject to change.
- The review shows a prevalent reversal effect of sentiment, where its impact on returns is typically reversed after 4–5 days. statistical
Source sentence
The study also showed the prevalence of the reversal effect of the sentiment, which means that the impact of sentiment on returns usually was reversed with the same magnitude after 4 or 5 days.
- The study could not quantitatively verify the hypothesis that sentiment improves R-squared due to lack of incremental R-squared data. statistical
Source sentence
The first hypothesis (RH1) concerning the improvement of the coefficient of determination cannot be directly verified quantitatively due to the lack of appropriate data (e.g. incremental R-squared).
Checked by others
No other paper in the archive has been found to support or contradict these findings. Coverage is partial, so this is neither replication nor refutation.
Code
No repository by the authors found in the paper.
Extracted 2026-11-14 · same card as JSON · A language model chose these items: check the source sentence before relying on one.